{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EWBWOAL534RGKPRGWHFFBV2DIG","short_pith_number":"pith:EWBWOAL5","schema_version":"1.0","canonical_sha256":"258367017ddf22653e26b1ca50d74341bfe7b8a4c2402ae405b2ef39492c7ff8","source":{"kind":"arxiv","id":"1605.08831","version":1},"attestation_state":"computed","paper":{"title":"Weighted Residuals for Very Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Falong Shen, Gang Zeng","submitted_at":"2016-05-28T02:13:32Z","abstract_excerpt":"Deep residual networks have recently shown appealing performance on many challenging computer vision tasks. However, the original residual structure still has some defects making it difficult to converge on very deep networks. In this paper, we introduce a weighted residual network to address the incompatibility between \\texttt{ReLU} and element-wise addition and the deep network initialization problem. The weighted residual network is able to learn to combine residuals from different layers effectively and efficiently. The proposed models enjoy a consistent improvement over accuracy and conve"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1605.08831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-28T02:13:32Z","cross_cats_sorted":[],"title_canon_sha256":"faea9dec1740bce89c3bea0c65da3065cbe8b0c1b792248aec5665b681e1caa4","abstract_canon_sha256":"5fa80740591770bca4c6833efa253b741bf8be4193fdda68a1e8d55e4da67822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:22.978554Z","signature_b64":"aoGwy4eb52yi5eEvAd/AbNi7Ybad0xoOjkHw62xmnY5Rg7yyk4cyfotTB0EwYAxGKhZsv6GeyWYA7baIuH/VCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"258367017ddf22653e26b1ca50d74341bfe7b8a4c2402ae405b2ef39492c7ff8","last_reissued_at":"2026-05-18T01:13:22.978007Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:22.978007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weighted Residuals for Very Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Falong Shen, Gang Zeng","submitted_at":"2016-05-28T02:13:32Z","abstract_excerpt":"Deep residual networks have recently shown appealing performance on many challenging computer vision tasks. However, the original residual structure still has some defects making it difficult to converge on very deep networks. In this paper, we introduce a weighted residual network to address the incompatibility between \\texttt{ReLU} and element-wise addition and the deep network initialization problem. The weighted residual network is able to learn to combine residuals from different layers effectively and efficiently. The proposed models enjoy a consistent improvement over accuracy and conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08831","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1605.08831","created_at":"2026-05-18T01:13:22.978097+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.08831v1","created_at":"2026-05-18T01:13:22.978097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08831","created_at":"2026-05-18T01:13:22.978097+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWBWOAL534RG","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWBWOAL534RGKPRG","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWBWOAL5","created_at":"2026-05-18T12:30:15.759754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11657","citing_title":"CNNtention: Can CNNs do better with Attention?","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG","json":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG.json","graph_json":"https://pith.science/api/pith-number/EWBWOAL534RGKPRGWHFFBV2DIG/graph.json","events_json":"https://pith.science/api/pith-number/EWBWOAL534RGKPRGWHFFBV2DIG/events.json","paper":"https://pith.science/paper/EWBWOAL5"},"agent_actions":{"view_html":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG","download_json":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG.json","view_paper":"https://pith.science/paper/EWBWOAL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.08831&json=true","fetch_graph":"https://pith.science/api/pith-number/EWBWOAL534RGKPRGWHFFBV2DIG/graph.json","fetch_events":"https://pith.science/api/pith-number/EWBWOAL534RGKPRGWHFFBV2DIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG/action/storage_attestation","attest_author":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG/action/author_attestation","sign_citation":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG/action/citation_signature","submit_replication":"https://pith.science/pith/EWBWOAL534RGKPRGWHFFBV2DIG/action/replication_record"}},"created_at":"2026-05-18T01:13:22.978097+00:00","updated_at":"2026-05-18T01:13:22.978097+00:00"}